Related Experiment Video
Updated: Dec 20, 2025
06:37
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
5.1K
Industry 4.0 Lean Shopfloor Management Characterization Using EEG Sensors and Deep Learning
Daniel Schmidt1,2, Javier Villalba Diez1,3,4, Joaquín Ordieres-Meré1
1Department of Business Intelligence, Escuela Técnica Superior de Ingenieros Industriales, Universidad Politécnica de Madrid, 28006 Madrid, Spain.
Sensors (Basel, Switzerland)
|May 24, 2020
Summary
This study used electroencephalography (EEG) to analyze brain activity during shopfloor management (SM) system use. Deep learning identified distinct neurological patterns, differentiating between goal-oriented and continuous improvement strategies for Industry 4.0.
Area of Science:
- Industrial Engineering
- Neuroscience
- Cognitive Science
Background:
- Industry 4.0 transformation requires active shopfloor integration.
- Shopfloor management (SM) systems are crucial for this integration.
- Existing SM systems fall into two main categories: goal-fixed (e.g., Balanced Scorecard) and continuous improvement-focused (e.g., Hoshin Kanri Tree).
Purpose of the Study:
- To differentiate between distinct shopfloor management (SM) systems by analyzing workers' neurological patterns.
- To evaluate the advantages and disadvantages of different SM approaches through brain activity analysis.
- To provide insights for Industry 4.0 leaders in selecting appropriate SM systems.
Main Methods:
- Utilized non-invasive electroencephalography (EEG) sensors to capture brain electrical activity.
- Employed a deep learning (DL) soft sensor for classifying recorded EEG data.
- Analyzed correlations within EEG signals to identify brain activity characteristics.
Main Results:
- Achieved 96.5% accuracy in classifying EEG data using the DL soft sensor.
- Detected significant differences and relevant characteristics in brain activity patterns corresponding to different SM systems.
- Demonstrated the feasibility of using neurophysiological data to distinguish between SM methodologies.
Conclusions:
- Neurological pattern analysis via EEG can effectively differentiate between various shopfloor management systems.
- Findings offer a novel method for assessing SM system effectiveness and guiding Industry 4.0 implementation.
- This research bridges neuroscience and industrial engineering to optimize shopfloor strategies.
